private void SkipPayload()
{
if (needToLoadPayload && payloadLength > 0)
{
proxStream.Seek(proxStream.GetFilePointer() + payloadLength);
}
needToLoadPayload = false;
}
private void AssertSameStreams(System.String msg, IndexInput expected, IndexInput test)
{
Assert.IsNotNull(expected, msg + " null expected");
Assert.IsNotNull(test, msg + " null test");
Assert.AreEqual(expected.Length(), test.Length(), msg + " length");
Assert.AreEqual(expected.GetFilePointer(), test.GetFilePointer(), msg + " position");
byte[] expectedBuffer = new byte[512];
byte[] testBuffer = new byte[expectedBuffer.Length];
long remainder = expected.Length() - expected.GetFilePointer();
while (remainder > 0)
{
int readLen = (int)System.Math.Min(remainder, expectedBuffer.Length);
expected.ReadBytes(expectedBuffer, 0, readLen);
test.ReadBytes(testBuffer, 0, readLen);
AssertEqualArrays(msg + ", remainder " + remainder, expectedBuffer, testBuffer, 0, readLen);
remainder -= readLen;
}
}
public void Read(Directory directory)
{
IndexInput input = directory.OpenInput(IndexFileNames.SEGMENTS);
try
{
int format = input.ReadInt();
if (format < 0)
{
// file contains explicit format info
// check that it is a format we can understand
if (format < FORMAT)
{
throw new System.IO.IOException("Unknown format version: " + format);
}
version = input.ReadLong(); // read version
counter = input.ReadInt(); // read counter
}
else
{
// file is in old format without explicit format info
counter = format;
}
for (int i = input.ReadInt(); i > 0; i--)
{
// read segmentInfos
SegmentInfo si = new SegmentInfo(input.ReadString(), input.ReadInt(), directory);
Add(si);
}
if (format >= 0)
{
// in old format the version number may be at the end of the file
if (input.GetFilePointer() >= input.Length())
{
version = (System.DateTime.Now.Ticks - 621355968000000000) / 10000;
}
// old file format without version number
else
{
version = input.ReadLong(); // read version
}
}
}
finally
{
input.Close();
}
}
private void Read(IndexInput input, System.String fileName)
{
int firstInt = input.ReadVInt();
if (firstInt < 0)
{
// This is a real format
format = firstInt;
}
else
{
format = FORMAT_PRE;
}
if (format != FORMAT_PRE & format != FORMAT_START)
{
throw new CorruptIndexException("unrecognized format " + format + " in file \"" + fileName + "\"");
}
int size;
if (format == FORMAT_PRE)
{
size = firstInt;
}
else
{
size = input.ReadVInt(); //read in the size
}
for (int i = 0; i < size; i++)
{
System.String name = StringHelper.Intern(input.ReadString());
byte bits = input.ReadByte();
bool isIndexed = (bits & IS_INDEXED) != 0;
bool storeTermVector = (bits & STORE_TERMVECTOR) != 0;
bool storePositionsWithTermVector = (bits & STORE_POSITIONS_WITH_TERMVECTOR) != 0;
bool storeOffsetWithTermVector = (bits & STORE_OFFSET_WITH_TERMVECTOR) != 0;
bool omitNorms = (bits & OMIT_NORMS) != 0;
bool storePayloads = (bits & STORE_PAYLOADS) != 0;
bool omitTermFreqAndPositions = (bits & OMIT_TERM_FREQ_AND_POSITIONS) != 0;
AddInternal(name, isIndexed, storeTermVector, storePositionsWithTermVector, storeOffsetWithTermVector, omitNorms, storePayloads, omitTermFreqAndPositions);
}
if (input.GetFilePointer() != input.Length())
{
throw new CorruptIndexException("did not read all bytes from file \"" + fileName + "\": read " + input.GetFilePointer() + " vs size " + input.Length());
}
}
/// <summary>Optimized implementation. </summary>
public virtual bool SkipTo(int target)
{
if (df >= skipInterval)
{
// optimized case
if (skipStream == null)
{
skipStream = (IndexInput)freqStream.Clone(); // lazily clone
}
if (!haveSkipped)
{
// lazily seek skip stream
skipStream.Seek(skipPointer);
haveSkipped = true;
}
// scan skip data
int lastSkipDoc = skipDoc;
long lastFreqPointer = freqStream.GetFilePointer();
long lastProxPointer = -1;
int numSkipped = -1 - (count % skipInterval);
while (target > skipDoc)
{
lastSkipDoc = skipDoc;
lastFreqPointer = freqPointer;
lastProxPointer = proxPointer;
if (skipDoc != 0 && skipDoc >= doc)
{
numSkipped += skipInterval;
}
if (skipCount >= numSkips)
{
break;
}
skipDoc += skipStream.ReadVInt();
freqPointer += skipStream.ReadVInt();
proxPointer += skipStream.ReadVInt();
skipCount++;
}
// if we found something to skip, then skip it
if (lastFreqPointer > freqStream.GetFilePointer())
{
freqStream.Seek(lastFreqPointer);
SkipProx(lastProxPointer);
doc = lastSkipDoc;
count += numSkipped;
}
}
// done skipping, now just scan
do
{
if (!Next())
{
return(false);
}
}while (target > doc);
return(true);
}
/// <summary> Read a particular segmentFileName. Note that this may
/// throw an IOException if a commit is in process.
///
/// </summary>
/// <param name="directory">-- directory containing the segments file
/// </param>
/// <param name="segmentFileName">-- segment file to load
/// </param>
public void Read(Directory directory, System.String segmentFileName)
{
bool success = false;
IndexInput input = directory.OpenInput(segmentFileName);
if (segmentFileName.Equals(IndexFileNames.SEGMENTS))
{
generation = 0;
}
else
{
#if !PRE_LUCENE_NET_2_0_0_COMPATIBLE
generation = Lucene.Net.Documents.NumberTools.ToLong(segmentFileName.Substring(1 + IndexFileNames.SEGMENTS.Length));
#else
generation = System.Convert.ToInt64(segmentFileName.Substring(1 + IndexFileNames.SEGMENTS.Length), 16);
#endif
}
lastGeneration = generation;
try
{
int format = input.ReadInt();
if (format < 0)
{
// file contains explicit format info
// check that it is a format we can understand
if (format < FORMAT_SINGLE_NORM_FILE)
{
throw new System.IO.IOException("Unknown format version: " + format);
}
version = input.ReadLong(); // read version
counter = input.ReadInt(); // read counter
}
else
{
// file is in old format without explicit format info
counter = format;
}
for (int i = input.ReadInt(); i > 0; i--)
{
// read segmentInfos
Add(new SegmentInfo(directory, format, input));
}
if (format >= 0)
{
// in old format the version number may be at the end of the file
if (input.GetFilePointer() >= input.Length())
{
version = System.DateTime.Now.Millisecond;
}
// old file format without version number
else
{
version = input.ReadLong(); // read version
}
}
success = true;
}
finally
{
input.Close();
if (!success)
{
// Clear any segment infos we had loaded so we
// have a clean slate on retry:
Clear();
}
}
}
private void Read(IndexInput input, System.String fileName)
{
int firstInt = input.ReadVInt();
if (firstInt < 0)
{
// This is a real format
format = firstInt;
}
else
{
format = FORMAT_PRE;
}
if (format != FORMAT_PRE & format != FORMAT_START)
{
throw new CorruptIndexException("unrecognized format " + format + " in file \"" + fileName + "\"");
}
int size;
if (format == FORMAT_PRE)
{
size = firstInt;
}
else
{
size = input.ReadVInt(); //read in the size
}
for (int i = 0; i < size; i++)
{
System.String name = StringHelper.Intern(input.ReadString());
byte bits = input.ReadByte();
bool isIndexed = (bits & IS_INDEXED) != 0;
bool storeTermVector = (bits & STORE_TERMVECTOR) != 0;
bool storePositionsWithTermVector = (bits & STORE_POSITIONS_WITH_TERMVECTOR) != 0;
bool storeOffsetWithTermVector = (bits & STORE_OFFSET_WITH_TERMVECTOR) != 0;
bool omitNorms = (bits & OMIT_NORMS) != 0;
bool storePayloads = (bits & STORE_PAYLOADS) != 0;
bool omitTermFreqAndPositions = (bits & OMIT_TERM_FREQ_AND_POSITIONS) != 0;
AddInternal(name, isIndexed, storeTermVector, storePositionsWithTermVector, storeOffsetWithTermVector, omitNorms, storePayloads, omitTermFreqAndPositions);
}
if (input.GetFilePointer() != input.Length())
{
throw new CorruptIndexException("did not read all bytes from file \"" + fileName + "\": read " + input.GetFilePointer() + " vs size " + input.Length());
}
}
internal SkipBuffer(IndexInput input, int length)
{
data = new byte[length];
pointer = input.GetFilePointer();
input.ReadBytes(data, 0, length);
}
public virtual void TestRandomAccessClones()
{
SetUp_2();
CompoundFileReader cr = new CompoundFileReader(dir, "f.comp");
// Open two files
IndexInput e1 = cr.OpenInput("f11");
IndexInput e2 = cr.OpenInput("f3");
IndexInput a1 = (IndexInput)e1.Clone();
IndexInput a2 = (IndexInput)e2.Clone();
// Seek the first pair
e1.Seek(100);
a1.Seek(100);
Assert.AreEqual(100, e1.GetFilePointer());
Assert.AreEqual(100, a1.GetFilePointer());
byte be1 = e1.ReadByte();
byte ba1 = a1.ReadByte();
Assert.AreEqual(be1, ba1);
// Now seek the second pair
e2.Seek(1027);
a2.Seek(1027);
Assert.AreEqual(1027, e2.GetFilePointer());
Assert.AreEqual(1027, a2.GetFilePointer());
byte be2 = e2.ReadByte();
byte ba2 = a2.ReadByte();
Assert.AreEqual(be2, ba2);
// Now make sure the first one didn't move
Assert.AreEqual(101, e1.GetFilePointer());
Assert.AreEqual(101, a1.GetFilePointer());
be1 = e1.ReadByte();
ba1 = a1.ReadByte();
Assert.AreEqual(be1, ba1);
// Now more the first one again, past the buffer length
e1.Seek(1910);
a1.Seek(1910);
Assert.AreEqual(1910, e1.GetFilePointer());
Assert.AreEqual(1910, a1.GetFilePointer());
be1 = e1.ReadByte();
ba1 = a1.ReadByte();
Assert.AreEqual(be1, ba1);
// Now make sure the second set didn't move
Assert.AreEqual(1028, e2.GetFilePointer());
Assert.AreEqual(1028, a2.GetFilePointer());
be2 = e2.ReadByte();
ba2 = a2.ReadByte();
Assert.AreEqual(be2, ba2);
// Move the second set back, again cross the buffer size
e2.Seek(17);
a2.Seek(17);
Assert.AreEqual(17, e2.GetFilePointer());
Assert.AreEqual(17, a2.GetFilePointer());
be2 = e2.ReadByte();
ba2 = a2.ReadByte();
Assert.AreEqual(be2, ba2);
// Finally, make sure the first set didn't move
// Now make sure the first one didn't move
Assert.AreEqual(1911, e1.GetFilePointer());
Assert.AreEqual(1911, a1.GetFilePointer());
be1 = e1.ReadByte();
ba1 = a1.ReadByte();
Assert.AreEqual(be1, ba1);
e1.Close();
e2.Close();
a1.Close();
a2.Close();
cr.Close();
}
internal SkipBuffer(IndexInput input, int length)
{
data = new byte[length];
pointer = input.GetFilePointer();
input.ReadBytes(data, 0, length);
}
public virtual void TestEncodeDecode()
{
int iterations = RandomInts.RandomInt32Between(Random, 1, 1000);
float AcceptableOverheadRatio = (float)Random.NextDouble();
int[] values = new int[(iterations - 1) * Lucene41PostingsFormat.BLOCK_SIZE + ForUtil.MAX_DATA_SIZE];
for (int i = 0; i < iterations; ++i)
{
int bpv = Random.Next(32);
if (bpv == 0)
{
int value = RandomInts.RandomInt32Between(Random, 0, int.MaxValue);
for (int j = 0; j < Lucene41PostingsFormat.BLOCK_SIZE; ++j)
{
values[i * Lucene41PostingsFormat.BLOCK_SIZE + j] = value;
}
}
else
{
for (int j = 0; j < Lucene41PostingsFormat.BLOCK_SIZE; ++j)
{
values[i * Lucene41PostingsFormat.BLOCK_SIZE + j] = RandomInts.RandomInt32Between(Random, 0, (int)PackedInt32s.MaxValue(bpv));
}
}
}
Directory d = new RAMDirectory();
long endPointer;
{
// encode
IndexOutput @out = d.CreateOutput("test.bin", IOContext.DEFAULT);
ForUtil forUtil = new ForUtil(AcceptableOverheadRatio, @out);
for (int i = 0; i < iterations; ++i)
{
forUtil.WriteBlock(Arrays.CopyOfRange(values, i * Lucene41PostingsFormat.BLOCK_SIZE, values.Length), new byte[Lucene41.ForUtil.MAX_ENCODED_SIZE], @out);
}
endPointer = @out.GetFilePointer();
@out.Dispose();
}
{
// decode
IndexInput @in = d.OpenInput("test.bin", IOContext.READ_ONCE);
ForUtil forUtil = new ForUtil(@in);
for (int i = 0; i < iterations; ++i)
{
if (Random.NextBoolean())
{
forUtil.SkipBlock(@in);
continue;
}
int[] restored = new int[Lucene41.ForUtil.MAX_DATA_SIZE];
forUtil.ReadBlock(@in, new byte[Lucene41.ForUtil.MAX_ENCODED_SIZE], restored);
Assert.AreEqual(Arrays.CopyOfRange(values, i * Lucene41PostingsFormat.BLOCK_SIZE, (i + 1) * Lucene41PostingsFormat.BLOCK_SIZE), Arrays.CopyOf(restored, Lucene41PostingsFormat.BLOCK_SIZE));
}
assertEquals(endPointer, @in.GetFilePointer());
@in.Dispose();
}
}
private void AssertSameStreams(System.String msg, IndexInput expected, IndexInput test)
{
Assert.IsNotNull(expected, msg + " null expected");
Assert.IsNotNull(test, msg + " null test");
Assert.AreEqual(expected.Length(), test.Length(), msg + " length");
Assert.AreEqual(expected.GetFilePointer(), test.GetFilePointer(), msg + " position");
byte[] expectedBuffer = new byte[512];
byte[] testBuffer = new byte[expectedBuffer.Length];
long remainder = expected.Length() - expected.GetFilePointer();
while (remainder > 0)
{
int readLen = (int) System.Math.Min(remainder, expectedBuffer.Length);
expected.ReadBytes(expectedBuffer, 0, readLen);
test.ReadBytes(testBuffer, 0, readLen);
AssertEqualArrays(msg + ", remainder " + remainder, expectedBuffer, testBuffer, 0, readLen);
remainder -= readLen;
}
}
/// <summary> Read a particular segmentFileName. Note that this may
/// throw an IOException if a commit is in process.
///
/// </summary>
/// <param name="directory">-- directory containing the segments file
/// </param>
/// <param name="segmentFileName">-- segment file to load
/// </param>
/// <throws> CorruptIndexException if the index is corrupt </throws>
/// <throws> IOException if there is a low-level IO error </throws>
public void Read(Directory directory, System.String segmentFileName)
{
bool success = false;
// Clear any previous segments:
Clear();
IndexInput input = directory.OpenInput(segmentFileName);
generation = GenerationFromSegmentsFileName(segmentFileName);
lastGeneration = generation;
try
{
int format = input.ReadInt();
if (format < 0)
{
// file contains explicit format info
// check that it is a format we can understand
if (format < CURRENT_FORMAT)
{
throw new CorruptIndexException("Unknown format version: " + format);
}
version = input.ReadLong(); // read version
counter = input.ReadInt(); // read counter
}
else
{
// file is in old format without explicit format info
counter = format;
}
for (int i = input.ReadInt(); i > 0; i--)
{
// read segmentInfos
Add(new SegmentInfo(directory, format, input));
}
if (format >= 0)
{
// in old format the version number may be at the end of the file
if (input.GetFilePointer() >= input.Length())
{
version = (System.DateTime.Now.Ticks - 621355968000000000) / 10000;
}
// old file format without version number
else
{
version = input.ReadLong(); // read version
}
}
success = true;
}
finally
{
input.Close();
if (!success)
{
// Clear any segment infos we had loaded so we
// have a clean slate on retry:
Clear();
}
}
}
public override FieldInfos Read(Directory directory, string segmentName, string segmentSuffix, IOContext iocontext)
{
string fileName = IndexFileNames.SegmentFileName(segmentName, "", PreFlexRWFieldInfosWriter.FIELD_INFOS_EXTENSION);
IndexInput input = directory.OpenInput(fileName, iocontext);
try
{
int format = input.ReadVInt32();
if (format > FORMAT_MINIMUM)
{
throw new IndexFormatTooOldException(input, format, FORMAT_MINIMUM, PreFlexRWFieldInfosWriter.FORMAT_CURRENT);
}
if (format < PreFlexRWFieldInfosWriter.FORMAT_CURRENT && format != PreFlexRWFieldInfosWriter.FORMAT_PREFLEX_RW)
{
throw new IndexFormatTooNewException(input, format, FORMAT_MINIMUM, PreFlexRWFieldInfosWriter.FORMAT_CURRENT);
}
int size = input.ReadVInt32(); //read in the size
FieldInfo[] infos = new FieldInfo[size];
for (int i = 0; i < size; i++)
{
string name = input.ReadString();
int fieldNumber = format == PreFlexRWFieldInfosWriter.FORMAT_PREFLEX_RW ? input.ReadInt32() : i;
byte bits = input.ReadByte();
bool isIndexed = (bits & PreFlexRWFieldInfosWriter.IS_INDEXED) != 0;
bool storeTermVector = (bits & PreFlexRWFieldInfosWriter.STORE_TERMVECTOR) != 0;
bool omitNorms = (bits & PreFlexRWFieldInfosWriter.OMIT_NORMS) != 0;
bool storePayloads = (bits & PreFlexRWFieldInfosWriter.STORE_PAYLOADS) != 0;
IndexOptions indexOptions;
if (!isIndexed)
{
indexOptions = IndexOptions.NONE;
}
else if ((bits & PreFlexRWFieldInfosWriter.OMIT_TERM_FREQ_AND_POSITIONS) != 0)
{
indexOptions = IndexOptions.DOCS_ONLY;
}
else if ((bits & PreFlexRWFieldInfosWriter.OMIT_POSITIONS) != 0)
{
if (format <= PreFlexRWFieldInfosWriter.FORMAT_OMIT_POSITIONS)
{
indexOptions = IndexOptions.DOCS_AND_FREQS;
}
else
{
throw new CorruptIndexException("Corrupt fieldinfos, OMIT_POSITIONS set but format=" + format + " (resource: " + input + ")");
}
}
else
{
indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
}
// LUCENE-3027: past indices were able to write
// storePayloads=true when omitTFAP is also true,
// which is invalid. We correct that, here:
if (indexOptions != IndexOptions.DOCS_AND_FREQS_AND_POSITIONS)
{
storePayloads = false;
}
DocValuesType normType = isIndexed && !omitNorms ? DocValuesType.NUMERIC : DocValuesType.NONE;
if (format == PreFlexRWFieldInfosWriter.FORMAT_PREFLEX_RW && normType != DocValuesType.NONE)
{
// RW can have norms but doesn't write them
normType = input.ReadByte() != 0 ? DocValuesType.NUMERIC : DocValuesType.NONE;
}
infos[i] = new FieldInfo(name,
isIndexed,
fieldNumber,
storeTermVector,
omitNorms,
storePayloads,
indexOptions,
DocValuesType.NONE,
normType,
null);
}
if (input.GetFilePointer() != input.Length)
{
throw new CorruptIndexException("did not read all bytes from file \"" + fileName + "\": read " + input.GetFilePointer() + " vs size " + input.Length + " (resource: " + input + ")");
}
return(new FieldInfos(infos));
}
finally
{
input.Dispose();
}
}
